Image de couverture de livre

Using LLMs as prompt modifier to avoid biases in AI image generators

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Peinl, René
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Computer Vision and Pattern Recognition Computers and Society
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

VLM@school -- Evaluation of AI image understanding on German middle school knowledge
par: Peinl, René, et autres
Publié: (2025)

Reverse Stable Diffusion: What prompt was used to generate this image?
par: Croitoru, Florinel-Alin, et autres
Publié: (2023)

Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images
par: Fraser, Kathleen C., et autres
Publié: (2024)

AI-generated data contamination erodes pathological variability and diagnostic reliability
par: He, Hongyu, et autres
Publié: (2026)

Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection
par: Yan, Zehong, et autres
Publié: (2025)

FairAdapter: Detecting AI-generated Images with Improved Fairness
par: Ding, Feng, et autres
Publié: (2024)

Architecture inside the mirage: evaluating generative image models on architectural style, elements, and typologies
par: Magrill, Jamie, et autres
Publié: (2026)

A Survey on Responsible Generative AI: What to Generate and What Not
par: Gu, Jindong
Publié: (2024)

Who Gets Flagged? The Pluralistic Evaluation Gap in AI Content Watermarking
par: Nemecek, Alexander, et autres
Publié: (2026)

Stable Signer: Hierarchical Sign Language Generative Model
par: Fang, Sen, et autres
Publié: (2025)

Large Language Models and Provenance Metadata for Determining the Relevance of Images and Videos in News Stories
par: Peterka, Tomas, et autres
Publié: (2025)

Are Vision Language Models Cross-Cultural Theory of Mind Reasoners?
par: Nazi, Zabir Al, et autres
Publié: (2025)

The Aftermath of DrawEduMath: Vision Language Models Underperform with Struggling Students and Misdiagnose Errors
par: Lucy, Li, et autres
Publié: (2026)

ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation
par: Jha, Akshita, et autres
Publié: (2024)

A Unified Framework and Dataset for Assessing Societal Bias in Vision-Language Models
par: Sathe, Ashutosh, et autres
Publié: (2024)

The Use of Multimodal Large Language Models to Detect Objects from Thermal Images: Transportation Applications
par: Ashqar, Huthaifa I., et autres
Publié: (2024)

FigSIM: A Dataset for Fine-grained Suicide Severity and Figurative Language in Suicide Memes
par: Chen, Liuliu, et autres
Publié: (2026)

ERIT Lightweight Multimodal Dataset for Elderly Emotion Recognition and Multimodal Fusion Evaluation
par: Frieske, Rita, et autres
Publié: (2024)

Restoring Ancient Ideograph: A Multimodal Multitask Neural Network Approach
par: Duan, Siyu, et autres
Publié: (2024)

Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering
par: Si, Chenglei, et autres
Publié: (2024)

MM-Soc: Benchmarking Multimodal Large Language Models in Social Media Platforms
par: Jin, Yiqiao, et autres
Publié: (2024)

A Longitudinal Analysis of Racial and Gender Bias in New York Times and Fox News Images and Articles
par: Ibrahim, Hazem, et autres
Publié: (2024)

Exploring Fusion Techniques in Multimodal AI-Based Recruitment: Insights from FairCVdb
par: Swati, Swati, et autres
Publié: (2024)

Using street view imagery and deep generative modeling for estimating the health of urban forests
par: Gupta, Akshit, et autres
Publié: (2025)

Scaling medical imaging report generation with multimodal reinforcement learning
par: Liu, Qianchu, et autres
Publié: (2026)

LLMs as World Models: Data-Driven and Human-Centered Pre-Event Simulation for Disaster Impact Assessment
par: Li, Lingyao, et autres
Publié: (2025)

ChatGPT as a mapping assistant: A novel method to enrich maps with generative AI and content derived from street-level photographs
par: Juhász, Levente, et autres
Publié: (2023)

Will we run out of data? Limits of LLM scaling based on human-generated data
par: Villalobos, Pablo, et autres
Publié: (2022)

Using street view images and visual LLMs to predict heritage values for governance support: Risks, ethics, and policy implications
par: Johansson, Tim, et autres
Publié: (2025)

Direction-Flipped Influence Audits Reveal Hidden Structure in Moral Choices of LLMs
par: Blandfort, Phil, et autres
Publié: (2026)

Representation Engineering: A Top-Down Approach to AI Transparency
par: Zou, Andy, et autres
Publié: (2023)

Towards objective and systematic evaluation of bias in artificial intelligence for medical imaging
par: Stanley, Emma A. M., et autres
Publié: (2023)

TrafficLens: Multi-Camera Traffic Video Analysis Using LLMs
par: Arefeen, Md Adnan, et autres
Publié: (2025)

Signformer is all you need: Towards Edge AI for Sign Language
par: Yang, Eta
Publié: (2024)

AI-Generated Fall Data: Assessing LLMs and Diffusion Model for Wearable Fall Detection
par: Alamgeer, Sana, et autres
Publié: (2025)

Dataset Scale and Societal Consistency Mediate Facial Impression Bias in Vision-Language AI
par: Wolfe, Robert, et autres
Publié: (2024)

An Efficient Sign Language Translation Using Spatial Configuration and Motion Dynamics with LLMs
par: Hwang, Eui Jun, et autres
Publié: (2024)

Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies
par: Gao, Yingqiang, et autres
Publié: (2024)

VideoNorms: Benchmarking Cultural Awareness of Video Language Models
par: Varimalla, Nikhil Reddy, et autres
Publié: (2025)

Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models
par: Girrbach, Leander, et autres
Publié: (2025)